Quantile Regression-Based Mean Estimation in Circular Systematic Sampling

The current study addresses a significant gap in sampling theory by introducing novel ratio-type estimators for finite population mean under circular systematic sampling using a quantile regression approach. We derive the theoretical mean squared error expressions for the proposed estimators and conduct comparative analyses against existing estimators. The results clearly demonstrate that our estimators outperform traditional ones in terms of efficiency. To validate our findings, we present numerical illustrations based on a real-life data set. Moreover, a Monte Carlo simulation study based on real-life data set is also included to check the performance of the proposed estimators. Numerical findings endorse the potential of the proposed estimators. The findings may help the researchers to get more estimates that are precise for population mean, which is widely applicable in different fields.